Zeyu Wang

22

Papers

259

Total Citations

Papers (22)

SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting

DiT4Edit: Diffusion Transformer for Image Editing

VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers

MemoNav: Working Memory Model for Visual Navigation

GS-ID: Illumination Decomposition on Gaussian Splatting via Adaptive Light Aggregation and Diffusion-Guided Material Priors

Mamba YOLO: A Simple Baseline for Object Detection with State Space Model

Spiking Point Transformer for Point Cloud Classification

Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training

Revisiting Adversarial Training at Scale

Rejuvenating image-GPT as Strong Visual Representation Learners

Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation

Masked Autoencoders Enable Efficient Knowledge Distillers

DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation

Towards Unique and Informative Captioning of Images

Multi-Query Video Retrieval

Highlight What You Want: Weakly-Supervised Instance-Level Controllable Infrared-Visible Image Fusion

ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba

Text2VDM: Text to Vector Displacement Maps for Expressive and Interactive 3D Sculpting

MagicColor: Multi-instance Sketch Colorization

RemDet: Rethinking Efficient Model Design for UAV Object Detection

An Inverse Scaling Law for CLIP Training

Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion